© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32913
    Prev
    Next
    INDEX
    Explanations

    explaining why something works or doesn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بÙĪد
    -0.07
    ä¸įéĶĻ
    -0.07
    è¯ģåĪ¸äº¤æĺĵæīĢ
    -0.07
    -bootstrap
    -0.06
    DidLoad
    -0.06
     CONSEQUENTIAL
    -0.06
    -errors
    -0.06
     totaled
    -0.06
    -names
    -0.06
     mined
    -0.06
    POSITIVE LOGITS
    为ä½ķ
    0.13
    为ä»Ģä¹Ī
    0.12
     why
    0.11
     mengapa
    0.11
    为ä»Ģä¹Īä¼ļ
    0.10
     Why
    0.10
    ä¹ĭæīĢ以
    0.09
    Why
    0.09
    why
    0.09
    为åķ¥
    0.09
    Activations Density 0.030%

    No Known Activations